Overall Survival Prediction of Diffuse large B-cell Lymphoma Using Deep Learning and Hematoxylin and Eosin Histological Images

Diffuse large B-cell lymphoma (DLBCL) is one of the most frequent subtypes of non-Hodgkin lymphoma (NHL). In approximately 40% of the patients, the prognosis and clinical evolution is unfavorable. This study is a proof-of-concept computer vision exercise to support the feasibility of predicting the prognosis of DLBCL using only hematoxylin and eosin (H&E) histological images and deep learning. A conventional series of DLBCL of 114 cases was split into two prognostic groups according to the overall survival (curve fitting and slope analysis): patients who died before the first 2 years (“Dead 2-years”, b1 = -0.054), and the others (b1 = -0.003). Twenty different convolutional neural networks (CNN) were used, and explainable artificial intelligence (XAI) was used to identify the areas of the images that the network used for classification. The final model based on DarkNet-19 predicted prognosis groups with high performance (test set accuracy = 96.26%). The other performance parameters were precision (94.46%), recall (95.02%), false positive rate (3.07%), specificity (96.93%), and F1 score (94.74%). XAI, including grad-CAM, occlusion sensitivity, and image-LIME confirmed that the CNN was focusing on the correct areas. Correlation with the clinicopathological characteristics found that the Dead < 2-years group was correlated with stage III-IV, International Prognostic Index (IPI) High + High/intermediate, progressive disease, non-GCB cell-of-origin, CD10-, BCL2+, and EBER+. Analysis of the immune microenvironment, cell cycle, and germinal center markers showed that Dead < 2-years had higher IL10, PD-L1, and CD163, and lower E2F1 protein expressions. In conclusion, the overall survival of DLBCL can be predicted using H&E histological images and deep learning. The trained CNN could be used as pre-trained CNN model for transfer learning in the future.